DocumentCode :
674983
Title :
Parallelized computation for Edge Histogram Descriptor using CUDA on the Graphics Processing Units (GPU)
Author :
Mohammadabadi, Alireza Ahmadi ; Chalechale, Abdollah ; Heidari, Hadi
Author_Institution :
Dept. of Comput. Eng., Razi Univ., Kermanshah, Iran
fYear :
2013
fDate :
30-31 Oct. 2013
Firstpage :
9
Lastpage :
14
Abstract :
Most image processing algorithms are inherently parallel, so multithreading processors are suitable in such applications. In huge image databases, image processing takes very long time for run on a single core processor because of single thread execution of algorithms. GPU is more common in most image processing applications due to multithread execution of algorithms, programmability and low cost. In this paper we show how to implement the MPRG-7 Edge Histogram Descriptor in parallel using CUDA programming model on a GPU. The Edge Histogram Descriptor describes the distribution of various types of edges with a histogram that can be a tool for image matching. This feature is applied to search images from a database which are similar to a query image. We evaluated the retrieval of the proposed technique using recall, precision, and average precision measures. Experimental results showed that parallel implementation led to an average speed up of 14.74×over the serial implementation. The average precision and the average recall of presented method are 67.02% and 55.00% respectively.
Keywords :
edge detection; graphics processing units; image matching; image retrieval; multi-threading; parallel architectures; visual databases; CUDA programming model; GPU; MPRG-7 edge histogram descriptor; average precision measures; graphics processing unit; image database; image matching; image processing algorithm; image searching; multithreading processors; parallelized computation; query image; recall measures; Feature extraction; Graphics processing units; Histograms; Image edge detection; Image retrieval; Instruction sets; Kernel; CUDA; GPU; content based image retrieval; edge histogram descriptor;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Architecture and Digital Systems (CADS), 2013 17th CSI International Symposium on
Conference_Location :
Tehran
Print_ISBN :
978-1-4799-0562-1
Type :
conf
DOI :
10.1109/CADS.2013.6714231
Filename :
6714231
Link To Document :
بازگشت